Assessment of three-dimensional adaptive mean shift and crown model in individual tree segmentation with LiDAR
DOI:
https://doi.org/10.35381/i.p.v7i13.4781Keywords:
Machine learning, forest inventories, technology assessment, (UNESCO Thesaurus)Abstract
This study aimed to evaluate the three-dimensional adaptive mean shift with a crown model for individual tree segmentation using LiDAR data collected by unmanned aerial vehicles. An open dataset was employed, and a parameter exploration based on allometric coefficients under an ellipsoidal model was conducted. Detected trees were matched with inventory points using distance-based criteria, and performance was measured through accuracy, recall, balance, and localization error. The results showed that trees at larger scales offered high completeness but low x due to over-segmentation, while smaller scales reversed this relationship. Plot-level analysis revealed differences by forest type: deciduous stands were more challenging due to irregular crowns, coniferous stands achieved nearly complete detection but produced false positives, and mixed stands offered the best balance. It was concluded that the method was effective and reproducible, although sensitive to parameterization.
Downloads
References
Álvarez Mendoza, C. I., Mollocana, J. G., y Gualotuna, D. (2024). Mapping of NDVI in Ecuador during the last 20 years using the Google Earth Engine cloud geospatial tool. En M. V. Garcia, C. Gordón-Gallegos, A. Salazar-Ramírez & C. Nuñez (Eds.), Proceedings of the International Conference on Computer Science, Electronics and Industrial Engineering (CSEI 2023). Springer Nature. https://doi.org/10.1007/978-3-031-70981-4_1
Aubry Kientz, M., Dutrieux, R., Ferraz, A., Saatchi, S., Hamraz, H., Williams, J., Coomes, D., Piboule, A., y Vincent, G. (2019). A comparative assessment of the performance of individual tree crowns delineation algorithms from ALS data in tropical forests. Remote Sensing, 11(9), 1086. https://doi.org/10.3390/rs11091086
Chen, W., Hu, X., Chen, W., Hong, Y., y Yang, M. (2018). Airborne LiDAR remote sensing for individual tree forest inventory using trunk detection-aided mean shift clustering techniques. Remote Sensing, 10(7), 1078. https://doi.org/10.3390/rs10071078
Comesaña Cebral, L., Martínez Sánchez, J., Lorenzo, H., & Arias, P. (2021). Individual tree segmentation method based on mobile backpack LiDAR point clouds. Sensors, 21(18), 6007. https://doi.org/10.3390/s21186007
Crowther, T. W., Glick, H. B., Covey, K. R., Bettigole, C., Maynard, D. S., Thomas, S. M., Bradford, M. A. (2015). Mapping tree density at a global scale. Nature, 525(7568), 201–205. https://doi.org/10.1038/nature14967
Deng, S., Jing, S., & Zhao, H. (2024). A hybrid method for individual tree detection in broadleaf forests based on UAV-LiDAR data and multistage 3D structure analysis. Forests, 15(6), 1043. https://doi.org/10.3390/f15061043
Dubrovin, I., Fortin, C., & Kedrov, A. (2024). An open dataset for individual tree detection in UAV LiDAR point clouds and RGB orthophotos in dense mixed forests. Scientific Reports, 14(1), 72669. https://doi.org/10.1038/s41598-024-72669-5
Ferraz, A., Saatchi, S., Mallet, C., & Meyer, V. (2016). Lidar detection of individual tree size in tropical forests. Remote Sensing of Environment, 183, 318–333. https://doi.org/10.1016/j.rse.2016.05.028
Henrich, J., van Delden, J., Seidel, D., Kneib, T., & Ecker, A. S. (2024). TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds. Ecological Informatics, 84, 102888. https://doi.org/10.1016/j.ecoinf.2024.102888
Hua, Z., Xu, S., & Liu, Y. (2022). Individual tree segmentation from side-view LiDAR point clouds of street trees using Shadow-Cut. Remote Sensing, 14(22), 5742. https://doi.org/10.3390/rs14225742
Hu, X., Chen, W., & Xu, W. (2017). Adaptive mean shift-based identification of individual trees using airborne LiDAR data. Remote Sensing, 9(2), 148. https://doi.org/10.3390/rs9020148
Hui, Z., Li, N., Xia, Y., Cheng, P., & He, Y. (2021). Individual tree extraction from UAV LiDAR point clouds based on self-adaptive mean shift segmentation. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V(1), 25–30. https://doi.org/10.5194/isprs-annals-V-1-2021-25-2021
Jakubowski, M. K., Li, W., Guo, Q., & Kelly, M. (2013). Delineating individual trees from lidar data: A comparison of vector- and raster-based segmentation approaches. Remote Sensing, 5(9), 4163–4186. https://doi.org/10.3390/rs5094163
Kandare, K., Ørka, H. O., Chan, J. C. W., & Dalponte, M. (2016). Effects of forest structure and airborne laser scanning point cloud density on 3D delineation of individual tree crowns. European Journal of Remote Sensing, 49(1), 337–359. https://doi.org/10.5721/EuJRS20164919
Lei, L., Yin, T., Chai, G., Li, Y., Wang, Y., Jia, X., & Zhang, X. (2022). A novel algorithm of individual tree crowns segmentation considering three-dimensional canopy attributes using UAV oblique photos. International Journal of Applied Earth Observation and Geoinformation, 112, 102893. https://doi.org/10.1016/j.jag.2022.102893
Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). PointNet: Deep learning on point sets for 3D classification and segmentation. En Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 77–85). IEEE. https://doi.org/10.1109/CVPR.2017.16
Tusa, E., Monnet, J. M., Barre, J. B., Dalla Mura, M., Dalponte, M., & Chanussot, J. (2021). Individual tree segmentation based on mean shift and crown shape model for temperate forest. IEEE Geoscience and Remote Sensing Letters, 18(12), 2052–2056. https://doi.org/10.1109/LGRS.2020.3012718
Xiao, W., Zaforemska, A., Smigaj, M., Wang, Y., & Gaulton, R. (2019). Mean shift segmentation assessment for individual forest tree delineation from airborne LiDAR data. Remote Sensing, 11(11), 1263. https://doi.org/10.3390/rs11111263
Xiao, W., Xu, S., Oude Elberink, S., & Vosselman, G. (2016). Individual tree crown modeling and change detection from airborne LiDAR data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3467–3477. https://doi.org/10.1109/JSTARS.2016.2541780
Yang, Z., Su, Y., Li, W., Cheng, K., Guan, H., Ren, Y., Hu, T., Xu, G., & Guo, Q. (2024). Segmenting individual trees from terrestrial LiDAR data using tree branch directivity. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 956–969. https://doi.org/10.1109/JSTARS.2023.3334014
Yan, W., Guan, H., Cao, L., Yu, Y., Li, C., & Lu, J. Y. (2020). A self-adaptive mean shift tree-segmentation method using UAV LiDAR data. Remote Sensing, 12(3), 515. https://doi.org/10.3390/rs12030515
You, H., Liu, Y., Lei, P., Qin, Z., & You, Q. (2023). Segmentation of individual mangrove trees using UAV-based LiDAR data. Ecological Informatics, 77, 102200. https://doi.org/10.1016/j.ecoinf.2023.102200
Yu, J., Lei, L., & Li, Z. (2024). Individual tree segmentation based on seed points detected by an adaptive crown shaped algorithm using UAV-LiDAR data. Remote Sensing, 16(5), 825. https://doi.org/10.3390/rs16050825
Zhu, L. (2024). GeoSep-PointNet++: A 3D point cloud semantic segmentation algorithm based on geometric information enhancement and feature separation encoding. En Proceedings of the 2024 IEEE 4th International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) (pp. 1514–1519). IEEE. https://doi.org/10.1109/ICIBA62489.2024.10869004
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Eduardo Alejandro Tusa-Jumbo, Tania Calle-Jimenez
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
CC BY-NC-SA : Esta licencia permite a los reutilizadores distribuir, remezclar, adaptar y construir sobre el material en cualquier medio o formato solo con fines no comerciales, y solo siempre y cuando se dé la atribución al creador. Si remezcla, adapta o construye sobre el material, debe licenciar el material modificado bajo términos idénticos.
OAI-PMH URL: https://fundacionkoinonia.com.ve/ojs/index.php/ingeniumetpotentia/oai
